Instructions to use mkhalifa/flan-t5-large-svamp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkhalifa/flan-t5-large-svamp with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mkhalifa/flan-t5-large-svamp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("mkhalifa/flan-t5-large-svamp")
model = AutoModelForSeq2SeqLM.from_pretrained("mkhalifa/flan-t5-large-svamp")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mkhalifa/flan-t5-large-svamp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mkhalifa/flan-t5-large-svamp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkhalifa/flan-t5-large-svamp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mkhalifa/flan-t5-large-svamp

SGLang

How to use mkhalifa/flan-t5-large-svamp with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mkhalifa/flan-t5-large-svamp" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkhalifa/flan-t5-large-svamp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mkhalifa/flan-t5-large-svamp" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkhalifa/flan-t5-large-svamp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mkhalifa/flan-t5-large-svamp with Docker Model Runner:
```
docker model run hf.co/mkhalifa/flan-t5-large-svamp
```

GRACE: Discriminator-Guided Chain-of-Thought Reasoning

This model is part of the work presented in the paper GRACE: Discriminator-Guided Chain-of-Thought Reasoning.

GRACE (Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator) is a stepwise decoding approach that steers the decoding process towards producing correct reasoning steps. It employs a step-level verifier or discriminator trained with a contrastive loss over correct and incorrect steps, which is used during decoding to score next-step candidates based on their correctness.

Resources

Paper: GRACE: Discriminator-Guided Chain-of-Thought Reasoning
GitHub Repository: https://github.com/mukhal/grace
Authors: Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

Sample Usage

The official implementation for running guided decoding using this model can be found in the GitHub repository. Below is an example of how to run the GRACE decoding:

WANDB_MODE=disabled python run_grace.py \
                        --model_name_or_path mkhalifa/flan-t5-large-gsm8k \
                        --in_file data/gsm8k/dev.jsonl \
                        --task gsm8k \
                        --disc_path ckpts/discrim/flan-t5-gsm8k/ \
                        --beta 0.1 --n_candidate_steps 20 --generation_type step-score \
                        --step_sampling_method top_p --device2 cuda:0 --top_p .95 --sample_calc true \
                        --max_steps 6  --max_step_length 60 --step_delimiter '|' --temperature .8  --n_self_consistency 1 --seed 42

Citation

If you use this work, please cite the following paper:

@article{khalifa2023grace,
  title={Grace: Discriminator-guided chain-of-thought reasoning},
  author={Khalifa, Muhammad and Logeswaran, Lajanugen and Lee, Moontae and Lee, Honglak and Wang, Lu},
  journal={arXiv preprint arXiv:2305.14934},
  year={2023}
}

Downloads last month: 7

Paper for mkhalifa/flan-t5-large-svamp

Discriminator-Guided Multi-step Reasoning with Language Models

Paper • 2305.14934 • Published May 24, 2023 • 1